Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5678 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.8120. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.3503. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.0976. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.8997. Min Act: -0.0000

Data Index: 386108 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.3952. Min Act: -0.0000

Data Index: 499813 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.3055. Min Act: -0.0000

Data Index: 1346541 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.3009. Min Act: -0.0000

Data Index: 245186 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.1818. Min Act: -0.0000

Data Index: 1334516 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.2677. Min Act: -0.0000

Data Index: 672334 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.2792. Min Act: -0.0000

Data Index: 1041471 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.1382. Min Act: -0.0000

Data Index: 994195 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.2517. Min Act: -0.0000

Data Index: 638133 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.2207. Min Act: -0.0000

Data Index: 734793 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.1851. Min Act: -0.0000

Data Index: 973635 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.1548. Min Act: -0.0000

Data Index: 663369 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.1523. Min Act: -0.0000

Data Index: 340858 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.0193. Min Act: -0.0000

Data Index: 25992 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.0211. Min Act: -0.0000

Data Index: 731862 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.1387. Min Act: -0.0000

Data Index: 618580 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 3.8120. Min Range: -3.8120

Max Act: 2.2277. Min Act: -0.0000

Data Index: 1073383 (C4 (Web Text))

Max Activating Token Index: 751